CohereGenerator

Generates text using Cohere's models through the Cohere generate endpoint.

Cohere generate API

Cohere discontinued the generate API, so this generator is a wrapper around CohereChatGenerator provided for backward compatibility.

Key Features

• Generates text using Cohere's command model family.
• Backward-compatible wrapper around CohereChatGenerator.
• Supports streaming responses with a configurable callback.
• Configurable via additional keyword arguments passed to the model.
• Works with PromptBuilder for dynamic prompt construction.
• Connects to DeepsetAnswerBuilder to build answers with references.

Configuration

Authentication

To use this component, connect Haystack Platform with Cohere first. For detailed instructions, see Use Cohere Models.

1. Drag the CohereGenerator component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the model name, for example command-r.
4. Go to the Advanced tab to configure the API key, API base URL, streaming callback, and additional model parameters.

Connections

CohereGenerator accepts a prompt string as input. It outputs a list of reply strings (replies) and request metadata (meta).

Connect PromptBuilder to the prompt input to build dynamic prompts. Connect the replies output to DeepsetAnswerBuilder to build answers with document references.

Usage Example

Basic Configuration

This is a simple example showing how to configure CohereGenerator:

components:
  CohereGenerator:
    type: haystack_integrations.components.generators.cohere.generator.CohereGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - COHERE_API_KEY
        - CO_API_KEY
        strict: false
      model: command-r
      streaming_callback:
      api_base_url:

Using the Component in a Pipeline

This pipeline uses CohereGenerator to generate replies to a question. It uses DeepsetAnswerBuilder to build the answers with references. It's also optimized for uploading files when testing it in Playground.

components:
  retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.open_search_hybrid_retriever.OpenSearchHybridRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: ''
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20 # The number of results to return
      fuzziness: 0
      embedder:
        type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
        init_parameters:
          normalize_embeddings: true
          model: intfloat/e5-base-v2

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: intfloat/simlm-msmarco-reranker
      top_k: 8

  meta_field_grouping_ranker:
    type: haystack.components.rankers.meta_field_grouping_ranker.MetaFieldGroupingRanker
    init_parameters:
      group_by: file_id
      subgroup_by:
      sort_docs_by: split_id

  prompt_builder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      required_variables: "*"
      template: |-
        You are a technical expert.
        You answer questions truthfully based on provided documents.
        If the answer exists in several documents, summarize them.
        Ignore documents that don't contain the answer to the question.
        Only answer based on the documents provided. Don't make things up.
        If no information related to the question can be found in the document, say so.
        Always use references in the form [NUMBER OF DOCUMENT] when using information from a document, e.g. [3] for Document [3] .
        Never name the documents, only enter a number in square brackets as a reference.
        The reference must only refer to the number that comes in square brackets after the document.
        Otherwise, do not use brackets in your answer and reference ONLY the number of the document without mentioning the word document.

        These are the documents:
        {%- if documents|length > 0 %}
        {%- for document in documents %}
        Document [{{ loop.index }}] :
        Name of Source File: {{ document.meta.file_name }}
        {{ document.content }}
        {% endfor -%}
        {%- else %}
        No relevant documents found.
        Respond with "Sorry, no matching documents were found, please adjust the filters or try a different question."
        {% endif %}

        Question: {{ question }}
        Answer:

  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm

  attachments_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      weights:
      top_k:
      sort_by_score: true

  CohereGenerator:
    type: haystack_integrations.components.generators.cohere.generator.CohereGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - COHERE_API_KEY
        - CO_API_KEY
        strict: false
      model: command-r
      streaming_callback:
      api_base_url:
  S3Downloader:
    type: haystack_integrations.components.downloaders.s3.s3_downloader.S3Downloader
    init_parameters:
      aws_access_key_id:
        type: env_var
        env_vars:
        - AWS_ACCESS_KEY_ID
        strict: false
      aws_secret_access_key:
        type: env_var
        env_vars:
        - AWS_SECRET_ACCESS_KEY
        strict: false
      aws_session_token:
        type: env_var
        env_vars:
        - AWS_SESSION_TOKEN
        strict: false
      aws_region_name:
        type: env_var
        env_vars:
        - AWS_DEFAULT_REGION
        strict: false
      aws_profile_name:
        type: env_var
        env_vars:
        - AWS_PROFILE
        strict: false
      boto3_config:
      file_root_path:
      file_extensions:
      file_name_meta_key: file_name
      max_workers: 32
      max_cache_size: 100
      s3_key_generation_function: deepset_cloud_custom_nodes.utils.storage.get_s3_key

connections:  # Defines how the components are connected
- sender: retriever.documents
  receiver: ranker.documents
- sender: ranker.documents
  receiver: meta_field_grouping_ranker.documents
- sender: prompt_builder.prompt
  receiver: answer_builder.prompt
- sender: meta_field_grouping_ranker.documents
  receiver: attachments_joiner.documents
- sender: attachments_joiner.documents
  receiver: answer_builder.documents

- sender: attachments_joiner.documents
  receiver: prompt_builder.documents
- sender: prompt_builder.prompt
  receiver: CohereGenerator.prompt
- sender: CohereGenerator.replies
  receiver: answer_builder.replies
- sender: retriever.documents
  receiver: S3Downloader.documents
- sender: S3Downloader.documents
  receiver: attachments_joiner.documents


inputs:  # Define the inputs for your pipeline
  query:  # These components will receive the query as input
  - "retriever.query"
  - "ranker.query"
  - "prompt_builder.question"
  - "answer_builder.query"

  filters:  # These components will receive a potential query filter as input
  - "retriever.filters_bm25"
  - "retriever.filters_embedding"

outputs:  # Defines the output of your pipeline
  documents: "attachments_joiner.documents"  # The output of the pipeline is the retrieved documents
  answers: "answer_builder.answers"  # The output of the pipeline is the generated answers

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
prompt	str		The prompt with instructions for the model.

Outputs

Parameter	Type	Default	Description
replies	List[str]		A list of replies generated by the model.
meta	List[Dict[str, Any]]		Information about the request.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var(['COHERE_API_KEY', 'CO_API_KEY'])	Cohere API key.
model	str	command-r	Cohere model to use for generation.
streaming_callback	Optional[Callable]	None	Callback function that is called when a new token is received from the stream. For more information, see Enable Streaming.
api_base_url	Optional[str]	None	Cohere base URL.
**kwargs	Any		Additional arguments passed to the model. These arguments are specific to the model. You can check them in model's documentation.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
prompt	str		The prompt with instructions for the model.